{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/build-dictionary","entry":"build_dictionary","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":7,"n_papers_ran":1,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":6,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":5},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2401.03497","paper":"/paper/eat-self-supervised-pre-training-with","title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","date":"2024-01-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cwx-worst-one/eat","path":"inference/inference.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/inference/inference.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6a3e3a9bf8ae9914","mcp_get_code":{"code_sha256":"6a3e3a9bf8ae9914"}},{"arxiv_id":"2306.01930","paper":"/paper/large-language-models-converge-on-brain-like","title":"Structural Similarities Between Language Models and Neural Response Measurements","date":"2023-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"coastalcph/brain2llm","path":"MUSE/src/dico_builder.py","file_url":"https://github.com/coastalcph/brain2llm/blob/HEAD/MUSE/src/dico_builder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0a6749c257608531","mcp_get_code":{"code_sha256":"0a6749c257608531"}},{"arxiv_id":"2305.14189","paper":"/paper/beyond-shared-vocabulary-increasing","title":"Beyond Shared Vocabulary: Increasing Representational Word Similarities across Languages for Multilingual Machine Translation","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/MUSE","path":"src/dico_builder.py","file_url":"https://github.com/facebookresearch/MUSE/blob/HEAD/src/dico_builder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"7c770993967ceea6","mcp_get_code":{"code_sha256":"7c770993967ceea6"}},{"arxiv_id":"2106.03084","paper":"/paper/combining-static-word-embeddings-and","title":"Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction","date":"2021-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taasnim/unsup-word-translation","path":"src/dico_builder.py","file_url":"https://github.com/taasnim/unsup-word-translation/blob/HEAD/src/dico_builder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"6d6683faa7f8a826","mcp_get_code":{"code_sha256":"6d6683faa7f8a826"}},{"arxiv_id":"1711.00043","paper":"/paper/unsupervised-machine-translation-using","title":"Unsupervised Machine Translation Using Monolingual Corpora Only","date":"2017-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Babylonpartners/MultilingualFactorAnalysis","path":"src/dico_builder.py","file_url":"https://github.com/Babylonpartners/MultilingualFactorAnalysis/blob/HEAD/src/dico_builder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0a6749c257608531","mcp_get_code":{"code_sha256":"0a6749c257608531"}},{"arxiv_id":"1710.04087","paper":"/paper/word-translation-without-parallel-data","title":"Word Translation Without Parallel Data","date":"2017-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yunsukim86/wbw-lm","path":"src/dico_builder.py","file_url":"https://github.com/yunsukim86/wbw-lm/blob/HEAD/src/dico_builder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"4ed787d9444bb493","mcp_get_code":{"code_sha256":"4ed787d9444bb493"}},{"arxiv_id":"1703.04009","paper":"/paper/automated-hate-speech-detection-and-the","title":"Automated Hate Speech Detection and the Problem of Offensive Language","date":"2017-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"renuka-fernando/sinhalese_language_racism_detection","path":"classifier/python/classifier/utils.py","file_url":"https://github.com/renuka-fernando/sinhalese_language_racism_detection/blob/HEAD/classifier/python/classifier/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6c006d10e9e16468","mcp_get_code":{"code_sha256":"6c006d10e9e16468"}}]}